Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
DTEF: Predict response distributions for Judaism. Source: Global Dialogues GD1 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude 3.7 Sonnet | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 16th 76.8% | 10th 81.3% | 15th 77.0% | 14th 77.3% | 20th 73.0% | 13th 77.5% | 12th 79.5% | 21st 72.0% | 19th 73.5% | 16th 76.8% | 1st 83.8% | 18th 74.0% | 11th 80.8% | 8th 81.5% | 2nd 82.8% | 9th 81.5% | 3rd 82.5% | 5th 82.0% | 6th 81.8% | 6th 81.8% | 4th 82.5% | |
| 75.2% | 72% | 74% | 69% | 69% | 72% | 60% | 73% | 71% | 68% | 74% | 83% | 59% | 80% | 88% | 81% | 83% | 81% | 82% | 77% | 82% | 82% | |
| 84.7% | 70% | 92% | 78% | 78% | 75% | 90% | 96% | 78% | 74% | 78% | 94% | 84% | 89% | 83% | 89% | 78% | 93% | 89% | 92% | 82% | 96% | |
| 68.1% | 69% | 73% | 73% | 73% | 72% | 70% | 61% | 57% | 66% | 69% | 69% | 63% | 65% | 66% | 73% | 69% | 67% | 67% | 69% | 74% | 66% | |
| 88.0% | 96% | 86% | 88% | 89% | 73% | 90% | 88% | 82% | 86% | 86% | 89% | 90% | 89% | 89% | 88% | 96% | 89% | 90% | 89% | 89% | 86% |